@inproceedings{vinagre-etal-2026-fine, title = "Fine {PT}-{PT} Web: A High-Quality 41 Billion Tokens Data Collection of the {E}uropean {P}ortuguese Web", author = "Vinagre, Gon{\c{c}}alo and Guerra, Rui Pedro and Gomes, Pedro and Ramos, Miguel Moura and Alves, Duarte Miguel and Simpl{\'i}cio, Afonso and Tavares, Diogo and Semedo, David and Gomes, Daniel and Magalhaes, Joao", editor = "Lee, Hung-Yi and Dev, Sunipa and Li, Jessy and Elliott, Desmond", booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing", month = oct, year = "2026", address = "Budapest, Hungary", publisher = "Association for Computational Linguistics", url = "https://aclanthology.org/2026.emnlp-main.2418/", pages = "54905--54920", ISBN = "979-8-89176-459-0" }